Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 919 records · Page 51Linked to original sources
PubMed1998

Artificial neural network for risk assessment in preterm neonates.

AIM: To predict the individual neonatal mortality risk of preterm infants using an artificial neural network "trained" on admission data. METHODS: A total of 890 preterm neonates (< 32 weeks gestational age and/or < 1500 g birthweight) were enrolled in our retrospective study. The neural network trained on infants born between 1990 and 1993. The predictive value was tested on infants born in the successive three years. RESULTS: The artificial neural network performed significantly better than a logistic regression model (area under the receiver operator curve 0.95 vs 0.92). Survival was associated with high morbidity if the predicted mortality risk was greater than 0.50. There were no preterm infants with a predicted mortality risk of greater than 0.80. The mortality risks of two non-survivors with birthweights > 2000 g and severe congenital disease had largely been underestimated. CONCLUSION: An artificial neural network trained on admission data can accurately predict the mortality risk for most preterm infants. However, the significant number of prediction failures renders it unsuitable for individual treatment decisions.

Area Under Curve↗
PubMed2005

On convergence conditions of an extended projection neural network.

The output trajectory convergence of an extended projection neural network was developed under the positive definiteness condition of the Jacobian matrix of nonlinear mapping. This note offers several new convergence results. The state trajectory convergence and the output trajectory convergence of the extended projection neural network are obtained under the positive semidefiniteness condition of the Jacobian matrix. Comparison and illustrative examples demonstrate applied significance of these new results.

Algorithms↗
PubMed1997

Phylogenetic reconstruction using an unsupervised growing neural network that adopts the topology of a phylogenetic tree.

We propose a new type of unsupervised, growing, self-organizing neural network that expands itself by following the taxonomic relationships that exist among the sequences being classified. The binary tree topology of this neutral network, contrary to other more classical neural network topologies, permits an efficient classification of sequences. The growing nature of this procedure allows to stop it at the desired taxonomic level without the necessity of waiting until a complete phylogenetic tree is produced. This novel approach presents a number of other interesting properties, such as a time for convergence which is, approximately, a lineal function of the number of sequences. Computer simulation and a real example show that the algorithm accurately finds the phylogenetic tree that relates the data. All this makes the neural network presented here an excellent tool for phylogenetic analysis of a large number of sequences.

Algorithms↗
PubMed1997

Prediction of posterior fossa tumor type in children by means of magnetic resonance image properties, spectroscopy, and neural networks.

Recent studies have explored characteristics of brain tumors by means of magnetic resonance spectroscopy (MRS) to increase diagnostic accuracy and improve understanding of tumor biology. In this study, a computer-based neural network was developed to combine MRS data (ratios of N-acetyl-aspartate, choline, and creatine) with 10 characteristics of tumor tissue obtained from magnetic resonance (MR) studies, as well as tumor size and the patient's age and sex, in hopes of further improving diagnostic accuracy. Data were obtained in 33 children presenting with posterior fossa tumors. The cases were analyzed by a neuroradiologist, who then predicted the tumor type from among three categories (primitive neuroectodermal tumor, astrocytoma, or ependymoma/other) based only on the data obtained via MR imaging. These predictions were compared with those made by neural networks that had analyzed different combinations of the data. The neuroradiologist correctly predicted the tumor type in 73% of the cases, whereas four neural networks using different datasets as inputs were 58 to 95% correct. The neural network that used only the three spectroscopy ratios had the least predictive ability. With the addition of data including MR imaging characteristics, age, sex, and tumor size, the network's accuracy improved to 72%, consistent with the predictions of the neuroradiologist who was using the same information. Use of only the analog data (leaving out information obtained from MR imaging), resulted in 88% accuracy. A network that used all of the data was able to identify 95% of the tumors correctly. It is concluded that a neural network provided with imaging data, spectroscopic data, and a limited amount of clinical information can predict pediatric posterior fossa tumor type with remarkable accuracy.

Astrocytoma↗
PubMed1995

Fuzzy neural networks: between functional equivalence and applicability.

Research in fuzzy neural networks, which started from application oriented fuzzy system tuning, then moving to the automatic generation of fuzzy systems from data, is reaching a more mature stage, especially after the proof of functional equivalence of certain fuzzy models and neural networks. It is essential that the applicability of such developments is explored emphasizing the directions that research should follow. It can be shown that the nearest prototype classifier is functionally equivalent to an alternative fuzzy classifier model. Efficient, hardware friendly training algorithms are developed for dynamic generation of an optimum number of nearest prototypes for neural classifiers which enable the generation of fuzzy systems in real time. These systems are tested with complex applications showing the simulation results.

Bayes Theorem↗
PubMed1999

Sensitization elicited by directly and indirectly acting dopaminergic agonists: comparison using neural network analysis.

The major aim of this work was to compare sensitized responses to amphetamine with those of apomorphine. This was done using both a univariant analysis of locomotor activity and a multivariant neural network analysis of five different behaviors. The neural network analysis compares the pattern of behaviors from a treated group to a set of patterns from control conditions and estimates the dose of drug in control conditions that best matches the pattern of behaviors of the treated group. Both methods indicated that repeated administration of 2.0 mg/kg amphetamine but not 0.5 mg/kg amphetamine resulted in sensitization to the administration of a 0.5 mg/kg amphetamine challenge given 10 days following the end of the sensitizing regimen. Both analyses indicated sensitization following repeated administration of 5 mg/kg apomorphine. Studies of cross sensitization were done using a neural network analysis that could distinguish patterns of behavior elicited by amphetamine from those elicited by apomorphine. Such studies indicated that apomorphine elicits an apomorphine-like response in animals sensitized to either apomorphine or amphetamine. In contrast, amphetamine produces an amphetamine-like response in animals sensitized to amphetamine and an apomorphine-like response in animals sensitized to apomorphine. The results indicate that neural network analysis may be a useful tool for analyzing drug effects on patterns of behavior.

Amphetamine↗
PubMed2004

[Study on the application of artificial neural network in analysing the risk factors of diabetes mellitus].

OBJECTIVE: To study the use of neural network in determining the risk factors of diseases. METHODS: With back-propagation neural network (BP network) as fitting model based upon data gathered from an epidemiological survey on diabetes mellitus and under the network structure of 22-6-1, the mean impact value (MIV) for each input variables and sequencing the factors according to their absolute MIVs were calculated. The results from BP network with multiple logistic regression analysis and log-linear model for united actions between factors were compared with optimizing Levenberg-Marquardt algorithm. RESULTS: By BP network analysis, the sequence of importance for the risk factors of diabetes mellitus became: faster pulse, diabetes mellitus family history, living longer in the investigated area, with medical record of nephropathy, having higher ratio for waist-to-hip, being male, with medical records of diseases as hyperlipoproteinmia, coronary heart disease, hypertension, high diastolic pressure, higher income, do no drink alcohol, age, higher systolic pressure, less educated, body mass index, with medical records of other diseases, physical exercise related to jobs smoking, occupation, with medical record for cerebrovascular disease, with medical record for liver disease etc. However, only 7 factors were statistically significant in multiple logistic regression analysis. The sequence of their importance appeared as: pulse, diabetes mellitus family history, the medical record of nephropathy, waist-to-hip ratio, the medical record of hypertension, work-place related exercise and age. The sequences of importance were almost the same between the two while the difference could partly be explained by the interaction among risk factors through log-linear model. CONCLUSION: Neural network could be used to analyze the risk factors of diseases and could assimilate more complicated relationships (main effects and interactions) between inputs and outputs, better than using the traditional methods.

Adult↗
PubMed1996

Prospective validation of artificial neural network trained to identify acute myocardial infarction.

BACKGROUND: Artificial neural networks apply non-linear statistics to pattern recognition problems. One such problem is acute myocardial infarction (AMI), a diagnosis which, in a patient presenting as an emergency, can be difficult to confirm. We report here a prospective comparison of the diagnostic accuracy of a network and that of physicians, on the same patients with suspected AMI. METHODS: Emergency department physicians who evaluated 1070 patients 18 years or older presenting to the emergency department of a teaching hospital in California, USA with anterior chest pain indicated whether they thought these patients had sustained a myocardial infarction. The network analysed the patient data collected by the physicians during their evaluations and also generated a diagnosis. FINDINGS: The physicians had a diagnostic sensitivity and specificity for myocardial infarction of 73.3% (95% confidence interval 63.3-83.3%) and 81.1% (78.7-83.5%), respectively, while the network had a diagnostic sensitivity and specificity of 96.0% (91.2-100%) and 96.0% (94.8-97.2%), respectively. Only 7% of patients had had an AMI, a low frequency but typical for anterior chest pain. INTERPRETATION: The application of non-linear neural computational analysis via an artificial neural network to the clinical diagnosis of myocardial infarction appears to have significant potential.

Chest Pain↗
PubMed2001

Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke.

CONTEXT: Rehospitalization following inpatient medical rehabilitation has important health and economic implications for patients who have experienced a stroke. OBJECTIVE: Compare logistic regression and neural networks in predicting rehospitalization at 3-6-month follow-up for patients with stroke discharged from medical rehabilitation. DESIGN: The study was retrospective using information from a national database representative of medical rehabilitation patients across the US. SETTING: Information submitted to the Uniform Data System for Medical Rehabilitation from 1997 and 1998 by 167 hospital and rehabilitation facilities from 40 states was examined. PARTICIPANTS: 9584 patient records were included in the sample. The mean age was 70.74 years (SD = 12.87). The sample included 51.6% females and was 77.6% non-Hispanic White with an average length of stay of 21.47 days (SD = 15.47). MAIN OUTCOME MEASURES: Hospital readmission from 80 to 180 days following discharge. RESULTS: Statistically significant variables (P <.05) in the logistic model included sphincter control, self-care ability, age, marital status, ethnicity and length of stay. Area under the ROC curves were 0.68 and 0.74 for logistic regression and neural network analysis, respectively. The Hosmer-Lemeshow goodness-of-fit chi-square was 11.32 (df = 8, P = 0.22) for neural network analysis and 16.33 (df = 8, P = 0.11) for logistic regression. Calibration curves indicated a slightly better fit for the neural network model. CONCLUSION: There was no statistically significant or practical advantage in predicting hospital readmission using neural network analysis in comparison to logistic regression for persons who experienced a stroke and received medical rehabilitation during the period of the study.

Aged↗
PubMedDate not supplied

Training simultaneous recurrent neural network with resilient propagation for static optimization.

This paper proposes a non-recurrent training algorithm, resilient propagation, for the Simultaneous Recurrent Neural network operating in relaxation-mode for computing high quality solutions of static optimization problems. Implementation details related to adaptation of the recurrent neural network weights through the non-recurrent training algorithm, resilient backpropagation, are formulated through an algebraic approach. Performance of the proposed neuro-optimizer on a well-known static combinatorial optimization problem, the Traveling Salesman Problem, is evaluated on the basis of computational complexity measures and, subsequently, compared to performance of the Simultaneous Recurrent Neural network trained with the standard backpropagation, and recurrent backpropagation for the same static optimization problem. Simulation results indicate that the Simultaneous Recurrent Neural network trained with the resilient backpropagation algorithm is able to locate superior quality solutions through comparable amount of computational effort for the Traveling Salesman Problem.

Algorithms↗
PubMed1992

Classification of crossed immunoelectrophoretic patterns using digital image processing and artificial neural networks.

A method is presented which makes it possible to present crossed immunoelectrophoretic patterns to an artificial neural network. The electrophoretic patterns are presented for the artificial neural network as three-dimensional vectors and it is shown that it is possible with this representation to train the network to learn the patterns and classify them. It was found that the ability to generalize was substantially increased by the addition of noise to the input patterns during training. Furthermore, the addition of noise decreased the number of presentations needed to reach the predetermined error level. The trained neural network was able to classify all distorted patterns correctly within an error range of 1%.

Image Processing, Computer-Assisted↗
PubMed2000

Artificial neural networks for classifying olfactory signals.

For practical applications, artificial neural networks have to meet several requirements: Mainly they should learn quick, classify accurate and behave robust. Programs should be user-friendly and should not need the presence of an expert for fine tuning diverse learning parameters. The present paper demonstrates an approach using an oversized network topology, adaptive propagation (APROP), a modified error function, and averaging outputs of four networks described for the first time. As an example, signals from different semiconductor gas sensors of an electronic nose were classified. The electronic nose smelt different types of edible oil with extremely different a-priori-probabilities. The fully-specified neural network classifier fulfilled the above mentioned demands. The new approach will be helpful not only for classifying olfactory signals automatically but also in many other fields in medicine, e.g. in data mining from medical databases.

Algorithms↗
PubMed1995

Quantification of biomedical NMR data using artificial neural network analysis: lipoprotein lipid profiles from 1H NMR data of human plasma.

Artificial neural network (ANN) analysis is a new technique in NMR spectroscopy. It is very often considered only as an efficient "black-box' tool for data classification, but we emphasize here that ANN analysis is also powerful for data quantification. The possibility of finding out the biochemical rationale controlling the ANN outputs is presented and discussed. Furthermore, the characteristics of ANN analysis, as applied to plasma lipoprotein lipid quantification, are compared to those of sophisticated lineshape fitting (LF) analysis. The performance of LF in this particular application is shown to be less satisfactory when compared to neural networks. The lipoprotein lipid quantification represents a regular clinical need and serves as a good example of an NMR spectroscopic case of extreme signal overlap. The ANN analysis enables quantification of lipids in very low, intermediate, low and high density lipoprotein (VLDL, IDL, LDL and HDL, respectively) fractions directly from a 1H NMR spectrum of a plasma sample in < 1 h. The ANN extension presented is believed to increase the value of the 1H NMR based lipoprotein quantification to the point that it could be the method of choice in some advanced research settings. Furthermore, the excellent quantification performance of the ANN analysis, demonstrated in this study, serves as an indication of the broad potential of neural networks in biomedical NMR.

Humans↗
PubMed2004

Impact of descriptor vector scaling on the classification of drugs and nondrugs with artificial neural networks.

The influence of preprocessing of molecular descriptor vectors for solving classification tasks was analyzed for drug/nondrug classification by artificial neural networks. Molecular properties were used to form descriptor vectors. Two types of neural networks were used, supervised multilayer neural nets trained with the back-propagation algorithm, and unsupervised self-organizing maps (Kohonen maps). Data were preprocessed by logistic scaling and histogram equalization. For both types of neural networks, the preprocessing step significantly improved classification compared to nonstandardized data. Classification accuracy was measured as prediction mean square error and Matthews correlation coefficient in the case of supervised learning, and quantization error in the case of unsupervised learning. The results demonstrate that appropriate data preprocessing is an essential step in solving classification tasks.

Algorithms↗
PubMedDate not supplied

Noninvasive diagnosis of mechanical failure of the implanted total artificial heart using neural network analysis of acoustic signals.

Acoustic signal measurement has been proposed as a noninvasive method of detecting mechanical failure of the implanted total artificial heart. However, differences in acoustic spectra obtained from undamaged and damaged devices may be difficult to distinguish using standard techniques, such as visual inspection or statistical analysis. A new technique, artificial neural network analysis, which has been used successfully on other problems of pattern recognition and classification, was applied to improve the detectability of the acoustic method. Acoustic signals were measured using two different devices in one damaged and one undamaged electrohydraulic total artificial heart, both in a mock circulation set-up and in animal experiments where they were implanted in eight post mortem sheep and the acoustic signal measured using a microphone placed at the skin surface. Spectra of the acoustic waveforms were calculated by discrete Fourier transformation and 400 values (representing the log magnitude in each 2.5 Hz band of the spectrum between 0 and 1 kHz) and used as input to the neural network. A three layer backpropagation neural network containing 400 input nodes, 20 intermediate nodes, and one output node was able to forms. The trained neural network then perfectly distinguished damaged waveforms from undamaged ones, with good separability. Because the neural network's output can take on a value between two extremes denoting damaged and undamaged states, it is possible to detect any progressive failure at relatively earlier stages. With multiple output node configuration, it could also classify the different types of damage using single acoustic signal waveforms.

Acoustics↗
PubMed1992

Bifurcation analysis of a neural network model.

This paper describes the analysis of the well known neural network model by Wilson and Cowan. The neural network is modeled by a system of two ordinary differential equations that describe the evolution of average activities of excitatory and inhibitory populations of neurons. We analyze the dependence of the model's behavior on two parameters. The parameter plane is partitioned into regions of equivalent behavior bounded by bifurcation curves, and the representative phase diagram is constructed for each region. This allows us to describe qualitatively the behavior of the model in each region and to predict changes in the model dynamics as parameters are varied. In particular, we show that for some parameter values the system can exhibit long-period oscillations. A new type of dynamical behavior is also found when the system settles down either to a stationary state or to a limit cycle depending on the initial point.

Biological Clocks↗
PubMedDate not supplied

[Ophthalmologic evaluation of VDT/PC operators: approach to the diagnosis with neural networks].

The present study was performed to build a neural network as a diagnostic tool to aid ophthalmologic examination of VDT/PC operators. The network was built on anamnesic and ophthalmologic data (visual acuity and mesopic vision, contrast sensitivity) from 278 VDT/pC operators and is able to predict 88% of total cases who need specialist attention, when ocular pathologies are also present, and 91% when only refraction defects are present. The tests chosen for this study are not useful to build a very sensitive discriminant model. This study confirm the absence for useful ophthalmologic tests in screening of VDT/PC operators, particularly when ocular pathologies are present without refractive errors. For their capacity to translate on a clinical-pratic plane knowledge obtained through studies conducted on large populations, the neural networks seem to be a good diagnostic tool.

Computer Terminals↗
PubMed2003

Fault detection and classification in chemical processes based on neural networks with feature extraction.

Feed forward neural networks are investigated here for fault diagnosis in chemical processes, especially batch processes. The use of the neural model prediction error as the residual for fault diagnosis of sensor and component is analyzed. To reduce the training time required for the neural process model, an input feature extraction process for the neural model is implemented. An additional radial basis function neural classifier is developed to isolate faults from the residual generated, and results are presented to demonstrate the satisfactory detection and isolation of faults using this approach.

Algorithms↗